MCP Server for ServiceNow

@mady22070

代码仓库

基本信息

分类

推理

传输方式

stdio

作者

mady22070

关于 MCP Server for ServiceNow

This MCP Server for ServiceNow is designed to be both generic and extensible. It leverages a modular approach to handle a wide range of ServiceNow use cases, from core ITSM operations to advanced CMDB management and dynamic workflow orchestration.

#servicenow #mcp-server #integration

MCP Server for ServiceNow 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "ServiceNowMCPServer": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

MCP Server for ServiceNow 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Server for ServiceNow?

MCP Server for ServiceNow is a generic, modular, and extensible MCP integration that exposes ServiceNow capabilities as tools for AI agents and external systems. It covers ITSM, ITOM, SAM, HAM, Enhanced CMDB, PPM, Employee Experience, Reporting, Analytics, dynamic tool registration, and workflow orchestration.

How to use MCP Server for ServiceNow?

Clone the repository, create a Python 3.7+ virtual environment, install dependencies (requests, fastapi, uvicorn, MCP SDK), set your ServiceNow instance URL and authentication method (basic or OAuth) in config.py, then run python main.py to start the server using standard I/O transport. Tools are invoked by sending JSON payloads specifying the tool name and arguments.

Key features of MCP Server for ServiceNow

Generic ServiceNow client with CRUD, queries, Basic & OAuth auth.
Modular architecture with separate domain modules (ITSM, ITOM, etc.).
Enhanced CMDB with validation, deduplication, relationship management, enrichment, and audit logging.
Dynamic tool registration, deregistration, and listing at runtime.
Workflow orchestration for coordinating complex multi-step processes.
Rich, configurable prompt templates for AI agent interactions.

Use cases of MCP Server for ServiceNow

Automate incident management (create, read, update, delete incidents) via AI agents.
Manage asset lifecycle (SAM license records, HAM asset records) from external orchestration tools.
Perform enhanced CMDB operations (create/query CI records, deduplicate, manage relationships, enrich data).
Trigger ITOM events and manage PPM projects through API-driven workflows.
Orchestrate multi-step access provisioning or other business processes using the workflow module.

常见问题

What authentication methods are supported?

The server supports both Basic Authentication and OAuth. Set `SN_AUTH_METHOD` in `config.py` to either `"basic"` or `"oauth"` and provide the corresponding credentials.

What are the runtime requirements?

Python 3.7 or higher is required, along with the packages `requests`, `fastapi`, `uvicorn`, and the MCP SDK.

How are tools invoked?

Tools are invoked by sending a JSON payload with a `name` field (the tool name) and an `arguments` object matching the tool’s input schema. The server uses standard I/O transport for development and testing.

Does the server support dynamic tool registration?

Yes, the `dynamic_tools` module allows registration, deregistration, and listing of new tools at runtime without server restart.

What is the default transport?

The MCP server uses standard I/O transport when started via `python main.py`, making it suitable for development and testing with MCP-compatible clients.

推理分类下的更多 MCP 服务器

quarkus-langchain4j-workshop

quarkusio

Quarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration

iFlytek Workflow MCP Server

iflytek

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

Agentic Tools MCP Server

Pimzino

A comprehensive Model Context Protocol (MCP) server providing AI assistants with powerful task management and agent memories capabilities with project-specific storage.

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

Agentic Swmm Workflow

Zhonghao1995

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,